A New Two-Stage Image Retrieval Algorithm with Convolutional Neural Network

With the rapid growth of available image resources in various areas, effective methods to search image are becoming increasingly important. In this paper we propose an effective two-stage image retrieval algorithm with Convolutional Neural Network (CNN) for image retrieval. Our idea is to modify existing neural network and fine-tune it. Firstly, we use the softmax classifier to classify the images. Then we search further in more detail under the corresponding categories of images. The experimental results show that the image matching speed of our method outperforms several state-of-the-art image retrieval algorithms on the CIFAR-10 and ImageNet datasets, which can speed up the retrieval of similar features, and improve the query efficiency, as well as be applied in real time. Corresponding Author: Yuhua Li, llyhua@126.com

[1]  Xin Liu,et al.  3-D Deployment Optimization for Heterogeneous Wireless Directional Sensor Networks on Smart City , 2019, IEEE Transactions on Industrial Informatics.

[2]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[3]  Wei Lu,et al.  Result diversification in image retrieval based on semantic distance , 2019, Inf. Sci..

[4]  Hongling Chen,et al.  Face Recognition Algorithm Based on VGG Network Model and SVM , 2019 .

[5]  Hanjiang Lai,et al.  Supervised Hashing for Image Retrieval via Image Representation Learning , 2014, AAAI.

[6]  Xianhua Zeng,et al.  Deep forest hashing for image retrieval , 2019, Pattern Recognit..

[7]  David Stutz,et al.  Neural Codes for Image Retrieval , 2015 .

[8]  Jun Zhang,et al.  Competitive and cooperative particle swarm optimization with information sharing mechanism for global optimization problems , 2015, Inf. Sci..

[9]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Svetlana Lazebnik,et al.  Multi-scale Orderless Pooling of Deep Convolutional Activation Features , 2014, ECCV.

[11]  Kaushik Roy,et al.  Going Deeper in Spiking Neural Networks: VGG and Residual Architectures , 2018, Front. Neurosci..

[12]  Yin Li,et al.  Learning Deep Structure-Preserving Image-Text Embeddings , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[14]  Xiaonan Luo,et al.  A new algorithm for product image search based on salient edge characterization , 2014, J. Assoc. Inf. Sci. Technol..

[15]  Guoliang Luo,et al.  Shape based local affine invariant texture characteristics for fabric image retrieval , 2018, Multimedia Tools and Applications.

[16]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Guoliang Luo,et al.  A new sketch-based 3D model retrieval method by using composite features , 2017, Multimedia Tools and Applications.

[18]  Qingquan Li,et al.  Instance Similarity Deep Hashing for Multi-Label Image Retrieval , 2018, ArXiv.

[19]  Jen-Hao Hsiao,et al.  Deep learning of binary hash codes for fast image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[20]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[22]  Ruimao Zhang,et al.  Cost-Effective Active Learning for Deep Image Classification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.